Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    information related to public appearances, activities, or events involving individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "appearance."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rals
    -0.88
    cise
    -0.82
    bern
    -0.80
    awks
    -0.78
    ça
    -0.76
    imb
    -0.75
    brace
    -0.75
    ythm
    -0.73
    hov
    -0.70
    bard
    -0.70
    POSITIVE LOGITS
    lihood
    0.77
     appearances
    0.77
     appearance
    0.74
     Discrimination
    0.71
     Appearance
    0.67
    æ³
    0.65
    earance
    0.64
    DragonMagazine
    0.62
    Grab
    0.62
    antly
    0.62
    Act Density 0.033%

    No Known Activations